← Faisal Alam Independent research

Independent research · Sports analytics

The Night the Garden Got Loud Again: A Data Story of Game 4

By Faisal Alam · November 16, 2026

Down 29 in Game 4 of the 2026 NBA Finals, the Knicks won 107-106. Using every shot from the play-by-play, this paper shows what made it possible: the Spurs' shooting fell from 60% before halftime to 21% after, on shots that were no harder. A simulation shows that if the Spurs had shot normally, the Knicks would have won only about 1 time in 100. At the low point, down 20 with 9:33 left, their chance of winning was 0.4%.

Abstract

In Game 4 of the 2026 NBA Finals, the New York Knicks trailed the San Antonio Spurs 81-52 and won 107-106, the largest comeback in Finals history. Using reported scores, win probability and shooting splits, this paper rebuilds the comeback and tests how unlikely it was. With 9:33 left, models gave New York a 0.4% chance. A Fisher's exact test shows the Spurs' drop in shooting from the first half to the second was significant (p ≈ 0.0002 for all shots, 0.018 for threes). A shot-level logistic regression on all 86 Spurs attempts finds that their odds of making a shot fell by about 84% after halftime even after controlling for shot location (odds ratio 0.16, p = 0.0003), while the Knicks showed no significant change. The comeback came from regression to the mean plus a Knicks defense that allowed 30 second-half points.

Introduction

In Game 4 of the 2026 NBA Finals, the New York Knicks came back from 29 points down to beat the San Antonio Spurs at Madison Square Garden. It is the largest comeback in Finals history (ESPN).

The stakes were high. New York had won Games 1 and 2, then lost Game 3 at home after a poor second half. A loss in Game 4 would have tied the series 2-2, with San Antonio holding the momentum. Instead, an OG Anunoby putback sealed the comeback, and the win gave New York a 3-1 lead. They closed the series in Game 5 on June 13, 94-90, winning their first title since 1973 (Revolt, Black America Web).

A note on perspective. I've been a Knicks fan my whole life, which until June meant I had never seen them win a title. The 1999 Finals loss to these same Spurs was before my time, but the Pacers ending our seasons in 2024 and again in 2025 was not. So I watched this game the way a lot of Knicks fans did: braced for it to go wrong. This paper tries to do two things at once. It measures the comeback as carefully as the data allows, and it's honest about what the comeback felt like. The analysis is in plain type. My own commentary is in italics, like this.

This paper asks two questions:

  1. How did the comeback happen? Which stretches, players and lineups closed a 29-point gap?

  2. How unlikely was it? Measured against win-probability models and historical base rates, how rare is a 29-point comeback, especially on the Finals stage?

Data and methods

The analysis uses public game data and asks how the margin changed over time, who changed it and how often teams in that spot win.

Data

Definitions

Approach

  1. Rebuild the score after every scoring play and split the comeback into phases.

  2. Compare shooting by half with Fisher's exact and binomial tests.

  3. Fit a shot-level logistic regression that controls for shot zone.

  4. Simulate the second half at normal shooting rates (Monte Carlo).

  5. Compute a win-probability curve with a Brownian-motion model.

  6. Use plus-minus to see who was on the floor for the swing.

Anatomy of the comeback

From 81-52 down with 9:40 left in the third quarter, the Knicks outscored San Antonio 55-25 over the final 21.5 minutes and won 107-106. By quarter, the Knicks' margin went −19, −8, +12 and +16.

2026-11-16T11:40:46.327464 image/svg+xml Matplotlib v3.11.2, https://matplotlib.org/ Q1 Q2 Q3 Q4 −30 −25 −20 −15 −10 −5 0 5 Knicks margin (pts) Tied 3:06 Q2 −29 9:40 Q3 −29 End Q3 −15 9:33 Q4 −20 Final +1 The Knicks fell behind by 29 twice and won by 1
Score rebuilt from Basketball Reference play-by-play, all 110 scoring plays · Game 4, June 10, 2026

The game breaks into four phases.

  1. The collapse (Q1 to 9:40 Q3). San Antonio led by 19 after one quarter and 76-49 at the half. Both are the largest leads by a road team in Finals history. The Spurs made 11 of their first 16 threes and 14 in the half, a Finals record. Karl-Anthony Towns picked up two fouls in the first 62 seconds. The deficit first reached 29 at 71-42 with 3:06 left in the second quarter, then hit 29 again at 81-52 early in the third.

  2. The third-quarter stand. New York held San Antonio to 14 points on 4-of-20 shooting in the quarter. A 13-0 run cut the gap to 90-75 by the end of the third. Stephon Castle's fourth foul at 10:09 sent him to the bench for nearly five minutes, and the deficit fell from 27 to 19 while he sat.

  3. The stall. The Knicks went scoreless for the first 2:27 of the fourth. A Victor Wembanyama putback at 9:33 made it 95-75, and models put the Spurs' win probability at 99.6%.

  4. The finish. New York closed on a 32-11 run over the final 9:33. Every one of its 32 fourth-quarter points came in that window. San Antonio shot 4 of 19 in the quarter. With the Spurs up 106-105, Fox grabbed a loose ball and broke away with about 11 seconds left. Instead of running the clock, he went for a layup, and OG Anunoby chased him down from behind and blocked it (CBS Sports, Athlon Sports). On the Knicks' final possession, Brunson's deep three hit the front rim, and Anunoby tipped it in with 1.2 seconds left. The block and the tip came 9.9 seconds apart.

At halftime, down 76-49, the Garden was as quiet as it had been in months (NBC Sports). Twenty-seven points in a Finals game doesn't feel like a deficit. It feels like a verdict. Then the third quarter started, the Spurs went 4 of 20, and somewhere in that 13-0 run came the feeling every Knicks fan knows and doesn't trust: wait, is this actually happening? The Wembanyama putback at 9:33 felt like the answer, and the answer was no. Then the Knicks went on a 32-11 run.

Who drove it

Two scorers and one defensive shift account for most of the swing. Brunson and Anunoby combined for 69 of New York's 107 points, while the Spurs' shooting fell apart after halftime.

PlayerTeamPointsShootingOther
Jalen BrunsonNYK3612 of 25 FG5 reb, 7 ast
OG AnunobyNYK3310 of 15 FG (7 of 9 3PT)Playoff career high; chase-down block on Fox; game-winning tip
Victor WembanyamaSAS249 of 25 FG13 reb

Offense: two players in the 30s. Brunson and Anunoby joined a short list of teammates who each scored 30-plus in a Finals game, a list that includes Kobe Bryant and Shaquille O'Neal (2002) and Clyde Drexler and Jerome Kersey (1990) (NBA.com). Brunson set the tempo, and Anunoby finished it: over the final 23:04 he went 8 of 8 from the field and 5 of 5 from three (CBS Sports).

Defense: the real engine. The scoring flip came mostly from stops. The Spurs shot 4 of 20 in the third quarter and 4 of 19 in the fourth, 8 of 39 (20.5%) for the half. From three, they went 3 of 17 after the break. Anunoby described the change as contests that were "just like 1% better" (NBC Sports).

Foul trouble. Both teams lost a key piece early. Towns had two fouls 62 seconds in. Castle's fourth foul at 10:09 of the third cost San Antonio its best perimeter defender for nearly five minutes, and the Knicks gained 8 points in that stretch. Off the bench, NBA.com's coverage singled out José Alvarado's boost in the fourth quarter.

Plus-minus: who was on the floor for the swing. Points tell who scored; plus-minus tells how the team did with each player on the court. Towns, Brunson, Hart and Alvarado formed the core of the comeback.

2026-11-16T11:40:46.392291 image/svg+xml Matplotlib v3.11.2, https://matplotlib.org/ Karl-Anthony Towns Jalen Brunson Josh Hart Jose Alvarado Ariel Hukporti Jordan Clarkson OG Anunoby Mikal Bridges Jeremy Sochan Landry Shamet Mitchell Robinson Miles McBride +17 +11 +11 +11 +3 +2 -1 -2 -6 -13 -14 -14 Towns was +17 in his minutes; three reserves were −13 or worse
Basketball Reference plus/minus, Game 4

Towns' +17 is the standout. His early foul trouble kept him off the floor while the Knicks fell behind, so his on/off gap is +33, the largest on either team. Robinson, McBride and Shamet were each −13 or worse, likely because much of their time came in the first half, when the Spurs couldn't miss. Anunoby scored 33 but was −1, because he played heavy minutes in both halves. On the Spurs' side, Castle was −11 on the floor and +10 off it, which supports the foul-trouble story (Basketball Reference). Plus-minus is noisy in a single game, since it reflects who a player shared the floor with and when, so it supports the story rather than proving it.

The Knicks' side of the swing. New York scored 49 points in the first half and 58 in the second. Its shooting rose from 15 of 37 (41%) to 21 of 40 (53%), and nearly all of that came from three: 4 of 12 before the break, 11 of 19 after. At the rim nothing changed (6 of 9 in each half). The three-point jump is meaningful on the court but not statistically significant by itself (Fisher's exact test, p ≈ 0.17), so the comeback's statistical signal is mostly on the Spurs' end.

Box scores flatten moments. Anunoby's line says 33 points. It doesn't say that with 11 seconds left he ran down Fox from behind to keep the game alive, or that his last two points came on a tip with 1.2 seconds left, off a Brunson three that didn't fall, in a building that had gone from silent to deafening in about 20 minutes of game time. Mike Brown called it "the most iconic shot in the history of New York basketball" (NBA.com). I'm not going to argue.

How unlikely was it?

At 95-75 with 9:33 left, the Knicks' win probability was 0.4%, about 1 in 250 (News Tribune/AP, BET). Game 4 broke or tied three Finals records, and only one playoff comeback has ever been bigger.

BenchmarkPrevious recordGame 4
Largest Finals comeback (full play-by-play era, since 1997)24 pts, Celtics vs. Lakers, 200829 pts
Largest halftime deficit overcome in a Finals game21 pts, Baltimore Bullets vs. Philadelphia, 194827 pts
Largest deficit after three quarters overcome in a Finals game15 pts, Bulls vs. Trail Blazers, 199215 pts (tied)
Largest comeback in any playoff game31 pts, Clippers vs. Warriors, 201929 pts (2nd)

Sources: NBA.com, Al Jazeera, Arizona Sports/AP.

Was the swing luck or something real?

The Spurs shot far above normal before halftime and far below it after. Over full halves, they made 14 of 26 threes (54%) before the break and 3 of 17 (18%) after it.

Test 1: Did their shooting really change? A one-sided Fisher's exact test on makes and misses by half gives p ≈ 0.018 for threes and p ≈ 0.0002 for all field goals (28 of 47 vs. 8 of 39). Both are well under the usual 0.05 cutoff, so the drop is statistically significant.

How Fisher's exact test works. Put the threes in a 2×2 table: made or missed, first half or second half. Now suppose the Spurs' true shooting never changed. Then their 17 made threes (out of 43) could have landed in either half purely by chance. The test counts every possible way to split those 17 makes between the 26 first-half and 17 second-half attempts, and finds the share of splits that put 14 or more makes in the first half. That share is the p-value, 0.018. "Exact" means it counts every arrangement instead of using an approximation, which matters with samples this small. The field-goal version works the same way with 36 makes across 47 and 39 attempts.

Test 2: Which half was abnormal? Each three was modeled as a weighted coin flip at a league-average rate of about 36% (an assumption), using the binomial distribution:

P(X \ge 14 \mid n = 26,\ p = 0.36) = \sum_{k=14}^{26} \binom{26}{k} (0.36)^k (0.64)^{26-k} \approx 0.048

What each symbol means:

How it's derived: if every shot is independent with the same make chance p, any one sequence with k makes has probability p^k × (1 − p)^(n − k). Multiplying by the number of such sequences gives the chance of exactly k makes. Adding over k = 14, 15 … 26 gives the chance of 14 or more. The second-half figure uses the same formula with n = 17, added over k = 0 to 3.

Reading the results. Both halves were unusual, in opposite directions, with the hot half slightly rarer. Looking only at the Spurs' first 16 threes (11 made) would make the start look like a 1-in-127 event. But that window was picked after the fact because it was hot, so full halves are the fair comparison. Threes alone can't separate luck from defense, so the next section looks at every shot.

Statistically, the first half was the Spurs playing above their heads. Emotionally, it was 24 minutes of watching nearly every shot go in. Both were true, and only one of them could last.

Luck or defense? A shot-level logistic regression

Even after accounting for where they shot from, the Spurs' odds of making a shot fell by about 84% after halftime (odds ratio 0.16, p = 0.0003). Their shot selection did not get worse, so worse looks can't explain the collapse.

Data. All 163 field-goal attempts were coded from the Basketball Reference play-by-play (86 Spurs, 77 Knicks), each with result, distance and shot type. The Spurs' totals match the box score: 36 of 86 overall and 17 of 43 from three (FantasyData box score). Each shot falls in one of three zones: at the rim (2-pointers from 0–3 ft), other 2-pointers (4+ ft) and threes.

Model. Each shot is a make (1) or miss (0), so the model is a logistic regression, which estimates how each factor changes the odds of a make:

\log \frac{P(\text{make})}{1 - P(\text{make})} = \beta_0 + \beta_1\,\text{SecondHalf} + \beta_2\,\text{Other2} + \beta_3\,\text{Three}

What each symbol means:

How it's derived: an ordinary straight-line regression can predict impossible probabilities, like 130%. Modeling the log-odds instead keeps every prediction between 0% and 100%. The β values are chosen to make the Spurs' actual sequence of 86 makes and misses as likely as possible (a method called maximum likelihood). They were solved for with the Newton-Raphson method in Python (NumPy and SciPy).

How to read a β: raise e (about 2.718) to its power to get an odds ratio. β₁ came out to about −1.8, and e^−1.8 ≈ 0.16. After halftime, the odds of a make were 0.16 times their first-half level for the same type of shot, about 84% lower. Because the zone switches sit in the same equation, β₁ compares like with like: rim shots with rim shots, threes with threes.

The Spurs' shots got easier, not harder. After halftime they took more shots at the rim (28% vs. 21%), fewer threes (44% vs. 55%), and slightly shorter shots on average (15.2 vs. 15.9 ft). Accuracy still fell in all three zones.

2026-11-16T11:40:46.434508 image/svg+xml Matplotlib v3.11.2, https://matplotlib.org/ At the rim (0–3 ft) Other 2-pointers (4+ ft) Three-pointers 80% 8/10 55% 6/11 54% 14/26 18% 2/11 27% 3/11 18% 3/17 The Spurs shot worse after halftime in every zone, most of all at the rim 1st half 2nd half
Basketball Reference play-by-play · all 86 Spurs field-goal attempts, Game 4

Results (Spurs).

TermOdds ratio95% CIp
Second half0.160.06–0.440.0003
Other 2-pointer (vs. rim)0.680.18–2.600.58
Three (vs. rim)0.520.16–1.690.28

A likelihood-ratio test for the second-half term gives χ² = 14.8 (df = 1, p = 0.0001). At their first-half zone rates, the Spurs' 39 second-half shots would have produced about 24 makes. They made 8.

The Knicks as a control. The same model for New York shows no significant change after halftime (odds ratio 1.57, 95% CI 0.61–4.04, p = 0.35). In a pooled model with both teams, the gap between the Spurs' change and the Knicks' change is significant (p = 0.0009). So the collapse wasn't something that hit both teams, like fatigue or the arena. It was specific to San Antonio.

Robustness. Six Spurs attempts were tip-ins taken within 3 seconds of a missed shot, which makes them less independent than other shots. Dropping them leaves the result essentially unchanged: odds ratio 0.18 (95% CI 0.06–0.49, p = 0.0009).

What it means. The rim is the tell. The Spurs made 8 of 10 at the rim before halftime and 2 of 11 after. Point-blank shots are the least luck-driven in basketball, so a collapse there points to contact and contests, the Knicks' interior defense, more than to chance. Threes (3 of 17) are noisier and fit both stories. The best reading is that the hot first half regressed toward normal, and New York's defense pushed it well below normal.

8 of 10 at the rim, then 2 of 11. This is the number that made me stop and re-check the data the first time I saw it. Layups aren't supposed to be where luck lives. Something changed in the paint after halftime, and you didn't need a model to feel it.

What if the Spurs had shot normally?

Replaying the Spurs' second half 200,000 times at roughly league-average shooting, the Knicks win only about 1% of the time. The comeback needed San Antonio's collapse. Knicks shot-making alone could not have produced it.

Method: a Monte Carlo simulation. Everything was held fixed except whether each Spurs second-half shot went in: the Knicks' 107 points, the Spurs' 76 first-half points and their 11 second-half free-throw points. Each of the Spurs' 34 second-half shots (tip-in follow-ups excluded) was re-rolled as a make or miss using an assumed make rate for its zone: 65% at the rim, 42% for other 2-pointers and 36% for threes. These are approximate league averages, not measured values. The Knicks win a replay if the Spurs finish under 107, and a tie counts as a 50/50 overtime.

2026-11-16T11:40:46.573757 image/svg+xml Matplotlib v3.11.2, https://matplotlib.org/ 20 30 40 50 60 70 Spurs points after halftime Actual: 30 0.9% of replays at or below Average: 47 points Shooting normally, the Spurs top their actual 30 points about 99% of the time
Monte Carlo simulation · 34 Spurs second-half shots re-rolled 200,000 times
Spurs' second-half make ratesAvg. Spurs 2nd-half pointsKnicks win
Their actual second-half rates (check)2871%
Approx. league average471.1%
Their own first-half rates61under 0.01%

The first row is a sanity check: at the Spurs' real second-half rates, the setup gives the Knicks the win most of the time, as happened. Moving the assumed league rates a few points either way gives a Knicks win chance between 0.5% and 2.4%.

Caveats. The simulation holds the Knicks' scoring fixed. In reality, more Spurs makes would have meant fewer Knicks fast breaks and long rebounds, which would likely push New York's odds even lower. Dropping tip-in follow-ups slightly understates the Spurs' scoring chances.

How it fits with the regression. The regression shows the Spurs' drop wasn't caused by worse shots. The simulation shows the drop was necessary for the comeback. Together, they point to the Spurs' collapse, driven by regression to the mean and the Knicks' defense, as the precondition, with the Knicks' 58-point second half as the finish.

This is the section I keep coming back to. In roughly 99 of 100 versions of that second half, the Spurs shoot like a normal NBA team, the series heads back to San Antonio tied 2-2, and nobody writes this paper. We got the one version where they didn't. As a fan, that's terrifying and wonderful at the same time.

Win probability, play by play

The Knicks' chance of winning stayed below 10% for 28 straight minutes, from midway through the second quarter to 5:20 left in the fourth. It bottomed out at 0.4% at 9:33 of the fourth, then climbed past 50% for the first time with 1:22 left. Pairing this curve with the regression above shows the comeback in two layers: the regression explains why it happened, and the win-probability curve shows when the odds turned.

Rebuilding the score. The free throws from the same play-by-play were added to the shot data, giving a running score after all 110 scoring plays. The rebuilt score matches every reported checkpoint exactly: 41-22 after one quarter, 76-49 at the half, 81-52 at 9:40 of the third, 90-75 after three, 95-75 at 9:33 and 107-106 final. It also shows the Knicks first fell behind by 29 late in the second quarter (71-42), not only in the third.

The model. The model treats the rest of the game as random drift. The final margin is assumed to be normally distributed around the current margin, with a spread that shrinks as the clock runs down:

P(\text{Knicks win}) = \Phi\left(\frac{M}{\sigma\sqrt{t/48}}\right)

This is a standard model in sports statistics, first proposed by statistician Hal Stern in 1994. What each symbol means:

The idea is that the margin drifts randomly from now until the buzzer. The spread of that drift is σ × √(t/48): it shrinks as the clock runs down, and it grows with the square root of time because random swings partly cancel out. Dividing M by that spread tells you how many "typical swings" the trailing team needs, and Φ turns that into a chance. At 9:33, down 20, the spread was about 7.5 points, so the Knicks needed a swing about 2.65 times larger than typical: roughly a 0.4% chance.

Two versions were run:

2026-11-16T11:40:46.650347 image/svg+xml Matplotlib v3.11.2, https://matplotlib.org/ Q1 Q2 Q3 Q4 0% 25% 50% 75% 100% 9:33 Q4, down 20: 0.4% (simple model: 0.045%) Anunoby tip, 1.2 s left: 99% The Knicks' win chance bottomed out at 0.4% with 9:33 left, then climbed to 99% Simple model (σ = 13.5 pts) Calibrated model (σ ≈ 16.9 pts)
Score rebuilt from Basketball Reference play-by-play (all field goals and free throws) · win probability from the model described above

What the curve shows.

Look at the right edge of that chart. 64% with 1:22 left, the first time all night the Knicks were favorites. Then Castle's two free throws drop it to 28%, and for the next 28 seconds every Knicks fan was quietly calculating how this would become the cruelest loss in franchise history. Then the chase-down block. Then the tip. Then 99%. Do you believe it? I watched it, I studied every number, and I'm still not sure I do.

Linking it to the regression. The flat stretch near zero, from late in the second quarter through the start of the fourth, is where the Knicks' defense was doing its work. The Spurs' 8-of-39 second half kept the deficit from growing, but the clock was still running. The curve only moves up once New York's offense started converting (32 fourth-quarter points), which is why the odds stayed low for so long even as the defense held.

Discussion

The numbers say Game 4 was historically rare, but not random. The 0.4% win probability shows what a model saw at 9:33. It doesn't capture who these Knicks were.

This team had done it before. Win-probability models treat every team in a given spot alike. New York had already erased a 22-point fourth-quarter deficit against Cleveland in Game 1 of the conference finals. Counting Game 4, the Knicks went 2-0 in these playoffs when trailing by 20+ in the fourth (WTOP/AP). A team-level history like that is exactly what a league-wide model leaves out.

The swing turned on stops, not threes. Comebacks are usually pictured as a flurry of three-pointers. This one was built on defense: San Antonio scored 30 points in the entire second half. The Knicks' 58-30 second half is a defensive line score as much as an offensive one.

Inexperience showed late. San Antonio is a young team that reached the Finals early. After the game, Spurs coach Mitch Johnson said his team "got away from" the style that built the lead in the third and fourth quarters. Their 3-of-17 second half from three shows it. The cold half was ordinary by itself (8.9% likely), but it came against a defense playing its best basketball of the night.

What the numbers can't measure. This paper doesn't model tempo, and it can't measure what it is like to play at Madison Square Garden as the visiting team with a series on the line. Players talk about that pressure. In 2023, after the Knicks beat Cleveland in the first round, Cavaliers center Jarrett Allen said the "lights were brighter than expected" while explaining his struggles; his scoring fell from 14.3 points per game in the regular season to 9.4 in that series (Bleacher Report). San Antonio was a young team in its first Finals, on the road at the Garden.

The closest thing to a pressure test in the data is free throws, the one shot defense can't affect. The Spurs made 6 of 6 before halftime and 11 of 14 after. Two of those misses came from Wembanyama with 1:47 left and the Spurs up 104-103. Brunson's basket at 1:22 then put New York ahead 105-104. Three misses is far too few to prove anything, but the timing fits the story the crowd would tell. Pressure and defense likely worked together, and the data can't pull them apart.

Tempo and momentum. Almost every account of this game uses these two words, and this paper measures neither directly. Tempo, the number of possessions per minute, would show whether New York sped the game up after halftime; estimating it needs turnover and rebound data this paper didn't extract. Momentum is harder. Statisticians have argued about it for decades as the "hot hand." A 1985 study by Gilovich, Vallone and Tversky concluded that shooting streaks were mostly an illusion. A 2018 reanalysis by Miller and Sanjurjo found a flaw in that method and revived evidence for a modest hot-hand effect. The fair reading is that momentum is real but smaller than it feels.

What the data here can show is where the game turned. The Knicks' 13-0 third-quarter run, from 81-52 to 81-65, came entirely while Castle sat with four fouls. In the fourth, New York scored nothing in the first 2:27, then all 32 of its points in the final 9:33. Whether those stretches were momentum or just clusters of good possessions, they are where the win-probability curve moved most.

Momentum is partly a story we tell after the fact. Our brains are built to find patterns in streaks. But I also know what it felt like to watch that 13-0 run happen, and the research lands somewhere I can live with: momentum is real, just smaller than it feels. On this night, it didn't need to be big. It only needed to show up for nine and a half minutes.

It decided the series. A Spurs win would have tied the series 2-2 with San Antonio holding the momentum. Instead New York led 3-1 and closed it out three days later. Teams leading a Finals 3-1 have almost always won the title, so Game 4 was the hinge of the championship.

Limitations

Conclusion

The Knicks' Game 4 win was the largest comeback in Finals history and a roughly 1-in-250 outcome at its decisive moment. The data point to one precondition: a Spurs collapse after halftime, from 28 of 47 shooting to 8 of 39, that a regression shows was not explained by harder shots. A simulation shows the comeback was nearly impossible without it, about 1% at normal shooting. Brunson's 36 and Anunoby's 33 turned those stops into points, and the result decided the series: New York led 3-1 and won its first title in 53 years three days later.

I've spent this paper trying to be precise about a game that didn't feel precise at all. The numbers say 29 points, 0.4%, about 1 in 100. What they can't capture is watching a franchise that taught its fans to expect heartbreak refuse, for one night, to deliver it. Three nights later, they were champions.

Code and data

For anyone who wants to check the work: the data and code behind every number in this paper. The data files open in Excel or Google Sheets; the scripts run in Python 3 (NumPy, pandas, SciPy and Matplotlib).

Sources